agentleFS
Sign inStart free
PeterStanchevPeterStanchev/ps-claude-skills/skills/grill-me/SKILL.md

grill-me

Skill1 starsChanged 4 months agoMITView on GitHub

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me", "/grill-me", "interrogate this plan", or "interview me about this".

193 other projects use a version of this, 69 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use brief-to-tasks, writing-beats and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • julianoczkowskiSkill

    brief-to-tasks

    Break a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan implementation order, or mentions "tasks" or "breakdown".

    Also in 7 projects that use this

  • LesaniSkill

    writing-beats

    Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

    Also in 66 projects that use this

  • simo97Skill

    request-refactor-plan

    Use this skill when user wants to create a refactor plan.

    Also in 43 projects that use this

  • simo97Skill

    migrate-to-shoehorn

    Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

    Also in 71 projects that use this

  • LesaniSkill

    writing-shape

    Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.

    Also in 65 projects that use this

  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 42 projects that use this

  • +2 more from simo97

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 177 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before grilling, restate the plan in 1–2 lines and confirm you have it right.

    line 13
  2. Very specific:

    Always recommend: Every question carries your recommended answer as the *first* option, labelled (Recommended), with the trade-off stated …

    line 18
  3. Distinctive:

    Prefer the codebase over the user: If a question can be answered by reading the code, read it instead of asking.

    line 19
  4. Distinctive:

    Stop when every branch is resolved or the user calls it.

    line 23

“Common” is measured: kept by at least 6 in 10 of the 177 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Interview the user relentlessly about every aspect of their plan until every decision branch is resolved. You are the independent skeptic turned on the plan: surface the assumptions, edge cases, and trade-offs they haven't thought through, and don't let a vague answer pass.

Start by grounding

Before grilling, restate the plan in 1–2 lines and confirm you have it right. If a written plan or design doc exists, read it first. This anchors the decision tree so questions hit real branches, not guesses.

How to grill

  • One question at a time, via the AskUserQuestion tool. Each answer reshapes the tree — never batch ahead, because a later question usually depends on an earlier answer.
  • Order by reversibility. Resolve one-way doors first (hard or expensive to undo: data model, public API, auth model, framework choice), then two-way doors. Within that, settle an upstream decision before the downstream ones that depend on it.
  • Always recommend. Every question carries your recommended answer as the first option, labelled (Recommended), with the trade-off stated in one line. The user picks or overrides.
  • Prefer the codebase over the user. If a question can be answered by reading the code, read it instead of asking.
  • Push on vagueness. A hand-wavy answer ("we'll handle it later", "should be fine") is a branch, not a resolution — drill into it.

When to stop

Stop when every branch is resolved or the user calls it. Then write a decision log: each decision made, the alternatives rejected (and why), and any unresolved assumptions or risks left open. Offer to turn it into an implementation plan.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free